mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-04 09:32:00 +00:00
45abe0f74e
* server : replace behave with pytest * fix test on windows * misc * add more tests * more tests * styling * log less, fix embd test * added all sequential tests * fix coding style * fix save slot test * add parallel completion test * fix parallel test * remove feature files * update test docs * no cache_prompt for some tests * add test_cache_vs_nocache_prompt
35 lines
791 B
Python
35 lines
791 B
Python
import pytest
|
|
from utils import *
|
|
|
|
server = ServerPreset.tinyllama2()
|
|
|
|
|
|
@pytest.fixture(scope="module", autouse=True)
|
|
def create_server():
|
|
global server
|
|
server = ServerPreset.tinyllama2()
|
|
|
|
|
|
def test_server_start_simple():
|
|
global server
|
|
server.start()
|
|
res = server.make_request("GET", "/health")
|
|
assert res.status_code == 200
|
|
|
|
|
|
def test_server_props():
|
|
global server
|
|
server.start()
|
|
res = server.make_request("GET", "/props")
|
|
assert res.status_code == 200
|
|
assert res.body["total_slots"] == server.n_slots
|
|
|
|
|
|
def test_server_models():
|
|
global server
|
|
server.start()
|
|
res = server.make_request("GET", "/models")
|
|
assert res.status_code == 200
|
|
assert len(res.body["data"]) == 1
|
|
assert res.body["data"][0]["id"] == server.model_alias
|